© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 142429
    Prev
    Next
    INDEX
    Explanations

    awning LED, winches, hoisting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vettel
    0.61
    ."),
    0.59
    ме
    0.58
     അത്
    0.58
     सलू
    0.57
     Ezekiel
    0.57
    橿
    0.57
     Aldi
    0.55
    t
    0.55
    ेडियम
    0.55
    POSITIVE LOGITS
    AS
    0.58
     jsou
    0.55
    ED
    0.53
     courants
    0.52
    OX
    0.52
     lamps
    0.52
    話を
    0.51
     housings
    0.50
    {
    0.50
    ő
    0.50
    Activations Density 0.001%

    No Known Activations